Dr.
Julian Eßer

Julian Eßer is a research associate in Robotics and AI at the Fraunhofer Institute for Material Flow and Logistics IML in Dortmund and scientific coordinator of the Embodied AI research group at the Lamarr Institute. After earning his bachelor’s and master’s degrees (with honors) in mechanical engineering from the University of Duisburg-Essen in 2018 and 2020, respectively, he completed his Ph.D. at TU Dortmund University in 2025 on learning-based control of highly dynamic robots. His research focuses on embodied AI, particularly at the intersection of robotics, reinforcement learning, and physics simulation.

Current research topics:

• Machine Learning for robust whole-body control of highly dynamic robots in uncertain environments and human-machine interaction
• Embedding knowledge into reinforcement learning to accelerate the training process and improve performance for real-world robotics settings
• Reducing the sim-to-real gap by more accurate robot simulation models with data-driven methods based on real-world data

Special interests:

The fascinating intersection of Embodied AI between robotics, reinforcement learning, and physics-based simulation for learning robust control of robots moving and interacting dynamically with their environments.